[IPV6]: multicast join and misc

Here is a simplified version of the patch to fix a bug in IPv6
multicasting. It:

1) adds existence check & EADDRINUSE error for regular joins
2) adds an exception for EADDRINUSE in the source-specific multicast
        join (where a prior join is ok)
3) adds a missing/needed read_lock on sock_mc_list; would've raced
        with destroying the socket on interface down without
4) adds a "leave group" in the (INCLUDE, empty) source filter case.
        This frees unneeded socket buffer memory, but also prevents
        an inappropriate interaction among the 8 socket options that
        mess with this. Some would fail as if in the group when you
        aren't really.

Item #4 had a locking bug in the last version of this patch; rather than
removing the idev->lock read lock only, I've simplified it to remove
all lock state in the path and treat it as a direct "leave group" call for
the (INCLUDE,empty) case it covers. Tested on an MP machine. :-)

Much thanks to HoerdtMickael <hoerdt@clarinet.u-strasbg.fr> who
reported the original bug.
Signed-off-by: NDavid L Stevens <dlstevens@us.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

net/ipv6/ipv6_sockglue.c

@@ -423,11 +423,12 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname,
 			psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
 			retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
 				&psin6->sin6_addr);
-			if (retv)
+			/* prior join w/ different source is ok */
+			if (retv && retv != -EADDRINUSE)
 				break;
 			omode = MCAST_INCLUDE;
 			add = 1;
-		} else /*IP_DROP_SOURCE_MEMBERSHIP */ {
+		} else /* MCAST_LEAVE_SOURCE_GROUP */ {
 			omode = MCAST_INCLUDE;
 			add = 0;
 		}

net/ipv6/mcast.c

@@ -188,6 +188,16 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, struct in6_addr *addr)
 	if (!ipv6_addr_is_multicast(addr))
 		return -EINVAL;
 
+	read_lock_bh(&ipv6_sk_mc_lock);
+	for (mc_lst=np->ipv6_mc_list; mc_lst; mc_lst=mc_lst->next) {
+		if ((ifindex == 0 || mc_lst->ifindex == ifindex) &&
+		    ipv6_addr_equal(&mc_lst->addr, addr)) {
+			read_unlock_bh(&ipv6_sk_mc_lock);
+			return -EADDRINUSE;
+		}
+	}
+	read_unlock_bh(&ipv6_sk_mc_lock);
+
 	mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL);
 
 	if (mc_lst == NULL)
@@ -349,6 +359,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 	struct ipv6_pinfo *inet6 = inet6_sk(sk);
 	struct ip6_sf_socklist *psl;
 	int i, j, rv;
+	int leavegroup = 0;
 	int err;
 
 	if (pgsr->gsr_group.ss_family != AF_INET6 ||
@@ -368,6 +379,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 
 	err = -EADDRNOTAVAIL;
 
+	read_lock_bh(&ipv6_sk_mc_lock);
 	for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) {
 		if (pgsr->gsr_interface && pmc->ifindex != pgsr->gsr_interface)
 			continue;
@@ -401,6 +413,12 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 		if (rv)		/* source not found */
 			goto done;
 
+		/* special case - (INCLUDE, empty) == LEAVE_GROUP */
+		if (psl->sl_count == 1 && omode == MCAST_INCLUDE) {
+			leavegroup = 1;
+			goto done;
+		}
+
 		/* update the interface filter */
 		ip6_mc_del_src(idev, group, omode, 1, source, 1);
 
@@ -453,9 +471,12 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 	/* update the interface list */
 	ip6_mc_add_src(idev, group, omode, 1, source, 1);
 done:
+	read_unlock_bh(&ipv6_sk_mc_lock);
 	read_unlock_bh(&idev->lock);
 	in6_dev_put(idev);
 	dev_put(dev);
+	if (leavegroup)
+		return ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group);
 	return err;
 }